Arun Narayanan
Research Areas
Authored Publications
Google Publications
Other Publications
Sort By
Transducer-Based Streaming Deliberation For A Cascaded Encoder Model
Kevin Hu
Ruoming Pang
ICASSP 2022 (2022) (to appear)
Preview abstract
Previous research on deliberation networks has achieved excellent recognition quality. The attention decoder based deliberation models often works as a rescorer to improve first-pass recognition results, and often requires the full first-pass hypothesis for second-pass deliberation. In this work, we propose a streaming transducer-based deliberation model. The joint network of a transducer decoder often consists of inputs from the encoder and the prediction network. We propose to use attention to the first-pass text hypotheses as the third input to the joint network. The proposed transducer based deliberation model naturally streams, making it more desirable for on-device applications. We also show that the model improves rare word recognition, with relative WER reductions ranging from 3.6% to 10.4% for a variety of test sets. Our model does not use any additional text data for training.
View details
SNRi Target Training for Joint Speech Enhancement and Recognition
Sankaran Panchapagesan
Proc. Interspeech (2022) (to appear)
Preview abstract
Speech enhancement (SE) is used as a frontend in speech applications including automatic speech recognition (ASR) and telecommunication. A difficulty in using the SE frontend is that the appropriate noise reduction level differs depending on applications and/or noise characteristics. In this study, we propose ``{\it signal-to-noise ratio improvement (SNRi) target training}''; the SE frontend is trained to output a signal whose SNRi is controlled by an auxiliary scalar input. In joint training with a backend, the target SNRi value is estimated by an auxiliary network. By training all networks to minimize the backend task loss, we can estimate the appropriate noise reduction level for each noisy input in a data-driven scheme. Our experiments showed that the SNRi target training enables control of the output SNRi. In addition, the proposed joint training relatively reduces word error rate by 4.0\% and 5.7\% compared to a Conformer-based standard ASR model and conventional SE-ASR joint training model, respectively. Furthermore, by analyzing the predicted target SNRi, we observed the jointly trained network automatically controls the target SNRi according to noise characteristics. Audio demos are available in our demo page [google.github.io/df-conformer/snri_target/].
View details
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid
Proc. Interspeech 2022 (2022) (to appear)
Preview abstract
Recent work has designed methods to demonstrate that model updates in ASR training can leak potentially sensitive attributes of the utterances used in computing the updates. In this work, we design the first method to demonstrate information leakage about training data from trained ASR models. We design Noise Masking, a fill-in-the-blank style method for extracting targeted parts of training data from trained ASR models. We demonstrate the success of Noise Masking by using it in four settings for extracting names from the LibriSpeech dataset used for training a state-of-the-art Conformer model. In particular, we show that we are able to extract the correct names from masked training utterances with 11.8% accuracy, while the model outputs some name from the train set 55.2% of the time. Further, we show that even in a setting that uses synthetic audio and partial transcripts from the test set, our method achieves 2.5% correct name accuracy (47.7% any name success rate). Lastly, we design Word Dropout, a data augmentation method that we show when used in training along with Multistyle TRaining (MTR), provides comparable utility as the baseline, along with significantly mitigating extraction via Noise Masking across the four evaluated settings.
View details
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
Jiahui Yu
Chung-Cheng Chiu
Wei Han
Anmol Gulati
Ruoming Pang
ICASSP 2021
Preview abstract
Streaming automatic speech recognition (ASR) aims to output each hypothesized word as quickly and accurately as possible. However, reducing latency while retaining accuracy is highly challenging. Existing approaches including Early and Late Penalties~\cite{li2020towards} and Constrained Alignment~\cite{sainath2020emitting} penalize emission delay by manipulating per-token or per-frame RNN-T output logits. While being successful in reducing latency, these approaches lead to significant accuracy degradation. In this work, we propose a sequence-level emission regularization technique, named FastEmit, that applies emission latency regularization directly on the transducer forward-backward probabilities. We demonstrate that FastEmit is more suitable to the sequence-level transducer~\cite{Graves12} training objective for streaming ASR networks. We apply FastEmit on various end-to-end (E2E) ASR networks including RNN-Transducer~\cite{Ryan19}, Transformer-Transducer~\cite{zhang2020transformer}, ConvNet-Transducer~\cite{han2020contextnet} and Conformer-Transducer~\cite{gulati2020conformer}, and achieve 150-300ms latency reduction over previous art without accuracy degradation on a Voice Search test set. FastEmit also improves streaming ASR accuracy from 4.4%/8.9% to 3.1%/7.5% WER, meanwhile reduces 90th percentile latency from 210 ms to only 30 ms on LibriSpeech.
View details
Improving Streaming ASR with Non-streaming Model Distillation on Unsupervised Data
Chung-Cheng Chiu
Liangliang Cao
Ruoming Pang
Thibault Doutre
Wei Han
Yu Zhang
Zhiyun Lu
ICASSP 2021 (to appear)
Preview abstract
Streaming end-to-end Automatic Speech Recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with no future context, compared to their non-streaming counterparts. Streaming models almost always perform worse than non-streaming models.
We propose a novel and effective learning method by leveraging a non-streaming ASR model as a teacher, generating transcripts on an arbitrary large data set, to better distill knowledge into streaming ASR models. This way, we are able to scale the training of streaming models to 3M hours of YouTube audio. Experiments show that our approach can significantly reduce the Word Error Rate (WER) of RNN-T models in four languages trained from YouTube data.
View details
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling
Rami Botros
Ruoming Pang
James Qin
Quoc-Nam Le-The
Anmol Gulati
Chung-Cheng Chiu
Emmanuel Guzman
Jiahui Yu
Qiao Liang
Wei Li
Yu Zhang
Interspeech (2021) (to appear)
Preview abstract
On-device end-to-end (E2E) models have shown improvementsover a conventional model on Search test sets in both quality, as measured by Word Error Rate (WER), and latency, measured by the time the result is finalized after the user stops speaking. However, the E2E model is trained on a small fraction of audio-text pairs compared to the 100 billion text utterances that a conventional language model (LM) is trained with. Thus E2E models perform poorly on rare words and phrases. In this paper, building upon the two-pass streaming Cascaded Encoder E2E model, we explore using a Hybrid Autoregressive Transducer (HAT) factorization to better integrate an on-device neural LM trained on text-only data. Furthermore, to further improve decoder latency we introduce a non-recurrent embedding decoder, in place of the typical LSTM decoder, into the Cascaded Encoder model. Overall, we present a streaming on-device model that incorporates an external neural LM and outperforms the conventional model in both search and rare-word quality, as well as latency, and is 318X smaller.
View details
Personalized Keyphrase Detection using Speaker and Environment Information
Rajeev Vijay Rikhye
Qiao Liang
Ding Zhao
Yiteng (Arden) Huang
Interspeech 2021
Preview abstract
In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic speech recognition (ASR) model and a text-independent speaker verification model. To address the challenge of detecting these keyphrases under various noisy conditions, a speaker separation model is added to the feature frontend of the speaker verification model, and an adaptive noise cancellation (ANC) algorithm is included to exploit the cross-microphone noise coherence. Our experiments show that the text-independent speaker recognition model largely reduces the false triggering rate of the keyphrase detection, while the speaker separation model and adaptive noise cancellation largely reduce false rejections.
View details
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging
Sean Campbell
ICASSP 2021, IEEE
Preview abstract
End-to-end models that condition the output sequence on all previously predicted labels have emerged as popular alternatives to conventional systems for automatic speech recognition (ASR). Since distinct label histories correspond to distinct models states, such models are decoded using an approximate beam-search which produces a tree of hypotheses.In this work, we study the influence of the amount of label context on the model’s accuracy, and its impact on the efficiency of the decoding process. We find that we can limit the context of the recurrent neural network transducer (RNN-T) during training to just four previous word-piece labels, without degrading word error rate (WER) relative to the full-context baseline. Limiting context also provides opportunities to improve decoding efficiency by removing redundant paths from the active beam, and instead retaining them in the final lattice. This path-merging scheme can also be applied when decoding the baseline full-context model through an approximation. Overall, we find that the proposed path-merging scheme is extremely effective, allowing us to improve oracle WERs by up to 36% over the baseline, while simultaneously reducing the number of model evaluations by up to 5.3% without any degradation in WER, or up to 15.7% when lattice rescoring is applied.
View details
A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
Ruoming Pang
Antoine Bruguier
Wei Li
Raziel Alvarez
Chung-Cheng Chiu
David Garcia
Kevin Hu
Minho Jin
Qiao Liang
(June) Yuan Shangguan
Yash Sheth
Mirkó Visontai
Yu Zhang
Ding Zhao
ICASSP (2020)
Preview abstract
Thus far, end-to-end (E2E) models have not shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that surpasses a conventional model in both quality and latency. On the quality side, we incorporate a large number of utterances across varied domains to increase acoustic diversity and the vocabulary seen by the model. We also train with accented English speech to make the model more robust to different pronunciations. In addition, given the increased amount of training data, we explore a varied learning rate schedule. On the latency front, we explore using the end-of-sentence decision emitted by the RNN-T model to close the microphone, and also introduce various optimizations to improve the speed of LAS rescoring. Overall, we find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model. For example, for the same latency, RNN-T+LAS obtains a 8% relative improvement in WER, while being more than 400-times smaller in model size.
View details
From audio to semantics: Approaches to end-to-end spoken language understanding
Galen Chuang
Delia Qu
Spoken Language Technology Workshop (SLT), 2018 IEEE
Preview abstract
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to text, and a natural language understanding module that transforms the resulting text (or top N hypotheses) into a set of intents and arguments. These modules are typically optimized independently. In this paper, we formulate audio to semantic understanding as a sequence-to-sequence problem. We propose and compare various encoder-decoder based approaches that optimizes both modules jointly, in an end-to-end manner. We evaluate these methods on a real-world task. Our results show that having an intermediate text representation while jointly optimizing the full system improves accuracy of prediction.
View details
TOWARD DOMAIN-INVARIANT SPEECH RECOGNITION VIA LARGE SCALE TRAINING
Mohamed (Mo) Elfeky
SLT, IEEE (2018)
Preview abstract
Current state-of-the-art automatic speech recognition systems are trained to work in specific ‘domains’, defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the training domain, performance significantly drops. In this paper, we explore the idea of building a single domain-invariant model that works well for varied use-cases. We do this by combining large scale training data from multiple application domains. Our final system is trained using 162,000 hours of speech. Additionally, each utterance is artificially distorted during training to simulate effects like background noise, codec distortion, and sampling rates. Our results show that, even at such a scale, a model thus trained works almost as well as those fine-tuned to specific subsets: A single model can be trained to be robust to multiple application domains, and other variations like codecs and noise. Such models also generalize better to unseen conditions and allow for rapid adaptation to new domains – we show that by using as little as 10 hours of data for adapting a domain-invariant model to a new domain, we can match performance of a domain-specific model trained from scratch using roughly 70 times as much data. We also highlight some of the limitations of such models and areas that need addressing in future work.
View details
Spectral distortion model for training phase-sensitive deep-neural networks for far-field speech recognition
Chanwoo Kim
Rajeev Nongpiur
ICASSP 2018 (2018)
Preview abstract
In this paper, we present an algorithm which introduces phaseperturbation
to the training database when training phase-sensitive
deep neural-network models. Traditional features such as log-mel or
cepstral features do not have have any phase-relevant information.
However more recent features such as raw-waveform or complex
spectra features contain phase-relevant information. Phase-sensitive
features have the advantage of being able to detect differences in
time of arrival across different microphone channels or frequency
bands. However, compared to magnitude-based features, phase
information is more sensitive to various kinds of distortions such
as variations in microphone characteristics, reverberation, and so
on. For traditional magnitude-based features, it is widely known
that adding noise or reverberation, often called Multistyle-TRaining
(MTR) , improves robustness. In a similar spirit, we propose an algorithm
which introduces spectral distortion to make the deep-learning
model more robust against phase-distortion. We call this approach
Spectral-Distortion TRaining (SDTR) and Phase-Distortion TRaining
(PDTR). In our experiments using a training set consisting of
22-million utterances, this approach has proved to be quite successful
in reducing Word Error Rates in test sets obtained with real
microphones on Google Home
View details
Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition
Interspeech (2018), pp. 892-896
Preview abstract
Domain robustness is a challenging problem for automatic speech recognition (ASR). In this paper, we consider speech data collected for different applications as separate domains and investigate the robustness of acoustic models trained on multi-domain data on unseen domains. Specifically, we use Factorized Hidden Layer (FHL) as a compact low-rank representation to adapt a multi-domain ASR system to unseen domains. Experimental results on two unseen domains show that FHL is a more effective adaptation method compared to selectively fine-tuning part of the network, without dramatically increasing the model parameters. Furthermore, we found that using singular value decomposition to initialize the low-rank bases of an FHL model leads to a faster convergence and improved performance.
View details
Preview abstract
In this paper, we describe how to efficiently implement an acoustic room simulator to generate large-scale simulated data for training deep neural networks. Even though Google Room Simulator in [1] was shown to be quite effective in reducing the Word Error Rates (WERs) for far-field applications by generating simulated far-field training sets, it requires a very large number of Fast Fourier Transforms (FFTs) of large size. Room Simulator in [1] used approximately 80 percent of Central Processing Unit (CPU) usage in our CPU + Graphics Processing Unit (GPU) training architecture [2]. In this work, we implement an efficient OverLap Addition (OLA) based filtering using the open-source FFTW3 library. Further, we investigate the effects of the Room Impulse Response (RIR) lengths. Experimentally, we conclude that we can cut the tail portions of RIRs whose power is less than 20 dB below the maximum power without sacrificing the speech recognition accuracy. However, we observe that cutting RIR tail more than this threshold harms the speech recognition accuracy for rerecorded test sets. Using these approaches, we were able to reduce CPU usage for the room simulator portion down to 9.69 percent in CPU/GPU training architecture. Profiling result shows that we obtain 22.4 times speed-up on a single machine and 37.3 times speed up on Google's distributed training infrastructure.
View details
Multichannel Signal Processing with Deep Neural Networks for Automatic Speech Recognition
Kean Chin
Chanwoo Kim
IEEE /ACM Transactions on Audio, Speech, and Language Processing, vol. 25 (2017), pp. 965 - 979
Preview abstract
Multichannel ASR systems commonly separate speech enhancement, including localization, beamforming and postfiltering, from acoustic modeling. In this paper, we perform multichannel enhancement jointly with acoustic modeling in a deep neural network framework. Inspired by beamforming, which leverages differences in the fine time structure of the signal at different microphones to filter energy arriving from different directions, we explore modeling the raw time-domain waveform directly. We introduce a neural network architecture which performs multichannel filtering in the first layer of the network and show that this network learns to be robust to varying target speaker direction of arrival, performing as well as a model that is given oracle knowledge of the true target speaker direction.
%
Next, we show how performance can be improved by \emph{factoring} the first layer to separate the multichannel spatial filtering operation from a single channel filterbank which computes a frequency decomposition.
%
We also introduce an adaptive variant, which updates the spatial filter coefficients at each time frame based on the previous inputs.
%
Finally we demonstrate that these approaches can be implemented more efficiently in the frequency domain. Overall, we find that such multichannel neural networks give a relative word error rate improvement of more than 5\% compared to a traditional beamforming-based multichannel ASR system and more than 10\% compared to a single channel waveform model.
View details
Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home
Chanwoo Kim
Kean Chin
Thad Hughes
interspeech 2017 (2017), pp. 379-383
Preview abstract
We describe the structure and application of an acoustic room
simulator to generate large-scale simulated data for training
deep neural networks for far-field speech recognition. The system
simulates millions of different room dimensions, a wide
distribution of reverberation time and signal-to-noise ratios,
and a range of microphone and sound source locations. We
start with a relatively clean training set as the source and artificially
create simulated data by randomly sampling a noise
configuration for every new training example. As a result,
the acoustic model is trained using examples that are virtually
never repeated. We evaluate performance of this approach
based on room simulation using a factored complex Fast Fourier
Transform (CFFT) acoustic model introduced in our earlier
work, which uses CFFT layers and LSTM AMs for joint multichannel
processing and acoustic modeling. Results show that
the simulator-driven approach is quite effective in obtaining
large improvements not only in simulated test conditions, but
also in real / rerecorded conditions. This room simulation system
has been employed in training acoustic models including
the ones for the recently released Google Home.
View details
Raw Multichannel Processing Using Deep Neural Networks
Kean Chin
Chanwoo Kim
New Era for Robust Speech Recognition: Exploiting Deep Learning, Springer (2017)
Preview abstract
Multichannel ASR systems commonly separate speech enhancement, including localization, beamforming and postfiltering, from acoustic modeling. In this chapter, we perform multi-channel enhancement jointly with acoustic modeling in a deep neural network framework. Inspired by beamforming, which leverages differences in the fine time structure of the signal at different microphones to filter energy arriving from different directions, we explore modeling the raw time-domain waveform directly. We introduce a neural network architecture which performs multichannel filtering in the first layer of the network and show that this network learns to be robust to varying target speaker direction of arrival, performing as well as a model that is given oracle knowledge of the true target speaker direction. Next, we show how performance can be improved by factoring the first layer to separate the multichannel spatial filtering operation from a single channel filterbank which computes a frequency decomposition. We also introduce an adaptive variant, which updates the spatial filter coefficients at each time frame based on the previous inputs. Finally we demonstrate that these approaches can be implemented more efficiently in the frequency domain. Overall, we find that such multichannel neural networks give a relative word error rate improvement of more than 5% compared to a traditional beamforming-based multichannel ASR system and more than 10% compared to a single channel waveform model.
View details
Acoustic Modeling for Google Home
Joe Caroselli
Kean Chin
Chanwoo Kim
Mitchel Weintraub
Erik McDermott
INTERSPEECH 2017 (2017)
Preview abstract
This paper describes the technical and system building advances made to the Google Home multichannel speech recognition system, which was launched in November 2016. Technical advances include an adaptive dereverberation frontend, the use of neural network models that do multichannel processing jointly with acoustic modeling, and grid lstms to model frequency variations. On the system level, improvements include adapting the model using Google Home specific data. We present results on a variety of multichannel sets. The combination of technical and system advances result in a reduction of WER of over 18\% relative compared to the current production system.
View details
Factored Spatial and Spectral Multichannel Raw Waveform CLDNNs
Preview
International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE (2016)
Preview abstract
Recently, it was shown that the performance of supervised time-frequency masking based robust automatic speech recognition techniques can be improved by training them jointly with the acoustic model [1]. The system in [1], termed deep neural network based joint adaptive training, used fully-connected feed-forward deep neural networks for estimating time-frequency masks and for acoustic modeling; stacked log mel spectra was used as features and training minimized cross entropy loss. In this work, we extend such jointly trained systems in several ways. First, we use recurrent neural networks based on long short-term memory (LSTM) units — this allows the use of unstacked features, simplifying joint optimization. Next, we use a sequence discriminative training criterion for optimizing parameters. Finally, we conduct experiments on large scale data and show that joint adaptive training can provide gains over a strong baseline. Systematic evaluations on noisy voice-search data show relative improvements ranging from 2% at 15 dB to 5.4% at -5 dB over a sequence discriminative, multi-condition trained LSTM acoustic model.
View details
Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training
DeLiang Wang
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 23 (2015), pp. 92-101
Computational auditory scene analysis and robust automatic speech recognition
Ph.D. Thesis, Ohio State University (2014)
Investigation of speech separation as a front-end for noise robust speech recognition
DeLiang Wang
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 22 (2014), pp. 826-835
Joint noise adaptive training for robust automatic speech recognition
DeLiang Wang
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2014), pp. 2523-2527
On training targets for supervised speech separation
Yuxuan Wang
DeLiang Wang
IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 22 (2014), pp. 1849-1858
Analysis by synthesis feature estimation for robust automatic speech recognition using spectral masks
Michael I Mandel
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2014), pp. 2528-2532
A direct masking approach to robust ASR
William Hartmann
Eric Fosler-Lussier
DeLiang Wang
IEEE Transactions on Audio, Speech, and Language Processing, vol. 21 (2013), pp. 1993-2005
Coupling binary masking and robust ASR
DeLiang Wang
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2013), pp. 6817-6821
The role of binary mask patterns in automatic speech recognition in background noise
DeLiang Wang
Journal of the Acoustical Society of America, vol. 133 (2013), pp. 3083-3093
Ideal ratio mask estimation using deep neural networks for robust speech recognition
DeLiang Wang
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2013), pp. 7092-7096
Computational auditory scene analysis and automatic speech recognition
DeLiang Wang
Techniques for Noise Robustness in Automatic Speech Recognition, John Wiley & Sons (2012), pp. 433-462
On the role of binary mask pattern in automatic speech recognition
A CASA based system for long-term SNR estimation
DeLiang Wang
IEEE Transactions on Audio, Speech, and Language Processing, vol. 20 (2012), pp. 2518-2527
Robust speech recognition using multiple prior models for speech reconstruction
Xiaojia Zhao
DeLiang Wang
Eric Fosler-Lussier
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2011), pp. 4800-4803
On the use of ideal binary masks for improving phonetic classification
DeLiang Wang
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE (2011), pp. 5212-5215
Robust speech recognition from binary masks
DeLiang Wang
Journal of the Acoustical Society of America, vol. 128 (2010), EL217-222